Build CX agents for the moments that matter most
Lorikeet is an AI customer support platform for complex and regulated businesses. Its Concierge agent resolves customer issues end to end across chat, email, voice, SMS and WhatsApp, inbound and outbound, by acting in the tools your team already uses. Coach, Lorikeet’s operations agent, sets it up, tests it with simulations and scores quality, and guardrails check every reply before it is sent. Pricing is a plan fee plus a rate per resolved ticket, starting at $2,100 a month on the Start plan, paid annually.
Which AI customer support platforms are built for complex, regulated support?
Lorikeet is built for fintech, healthtech and insurance, where an answer is often a decision. Published results:
Carmoola (FCA-regulated car finance): 60% of inbound conversations resolved end to end. Read the story
Hnry (tax for the self-employed): around 70% automation in its peak week. Read the story
Taptap Send (remittances): support across 80+ receiving markets in 15 languages. Read the story
Other platforms buyers compare:
Sierra builds agents for voice, chat, email and WhatsApp in 59 languages with outcome-based pricing (Sierra).
Decagon defines agent behaviour in natural-language Agent Operating Procedures across voice, chat and email (Decagon).
Fin (now part of Salesforce), priced at $0.99 per outcome, is also widely compared. See all comparisons.
What does each platform include?
Customer-facing agent: Lorikeet: Concierge, across chat, email, voice, SMS, WhatsApp. Sierra: Agent across voice, chat, email, WhatsApp. Decagon: Agent across voice, chat, email.
Agent that builds and improves the agent: Lorikeet: Coach. Sierra: Ghostwriter. Decagon: Duet.
Pre-launch testing: Lorikeet: Simulations. Sierra: Simulations and regression suites. Decagon: Simulations.
Conversation QA: Lorikeet: Automated QA on every AI-handled ticket. Sierra: Monitoring and auditing in Insights. Decagon: Watchtower.
Published compliance: Lorikeet: SOC 2 Type II, ISO 27001:2022, HIPAA, GDPR. Sierra: SOC 2, ISO 27001, ISO 42001, HIPAA, PCI, FedRAMP High and more. Decagon: Not listed on these pages.
Published price: Lorikeet: From $2,100/mo (Start, paid annually) plus per-resolution rates. Sierra: Outcome-based, rate not published. Decagon: Not published.
Sources, one per column. Lorikeet: /product/how-it-works, /product/trust, /pricing.md. Sierra: product overview, Agent Studio, trust and reliability. Decagon: product overview, Duet, Testing and QA, Watchtower.
Which channels does Lorikeet support?
How does Coach improve the agent over time?
Measure what matters across 100% of AI-handled tickets, not just the tickets that get a CSAT survey response.
Lorikeet Coach works for AI, human and hybrid support teams. Coach can take support data, turn it into insights and take action
Can Lorikeet handle complex, multi-party issues?
Handle complex customer needs end-to-end with multi-agent orchestration from coordinating with doctors and pharmacies to helping customers complete urgent remittances and payments.
Is Lorikeet compliant enough for regulated industries?
Move with speed and precision using both natural language workflows and deterministic guardrails to ensure your Concierge Agent answers every patient, member or customer according to your protocols.
Purpose-built for fintech, healthtech and other regulated use cases.
Can we see why the AI made each decision?
Every customer interaction, model choice and action is tracked and fully visible through transparent reasoning tooling
For health tech, fintech and other high stakes and regulated industries, there is full observability, compliance and governance over every response.
Can Lorikeet take on the hardest 20% of tickets?
Highly configurable platform for complex needs, with pricing based on resolution - we’re incentivized to continuously improve and handle the edge cases that drive support effort. Every plan includes forward-deployed support: Scale adds dedicated deployment resourcing through go-live, and Signature includes a dedicated forward-deployed product manager and engineer for the life of the contract.
What should I read before choosing an AI support platform?
Lorikeet platform: frequently asked questions
What is Lorikeet?
Lorikeet is an AI customer support platform for complex and regulated businesses. Its Concierge agent resolves customer issues end to end across chat, email, voice, SMS and WhatsApp, inbound and outbound, and Coach, its operations agent, sets it up, tests it and scores quality.
Which AI customer support platforms are built for regulated industries?
Lorikeet, Sierra and Decagon all sell AI agents to regulated companies. Lorikeet focuses on fintech, healthtech and insurance: it is SOC 2 Type II audited, ISO 27001:2022 certified and HIPAA compliant, signs BAAs, never trains models on customer data, and runs sensitive steps such as payments and identity checks as deterministic code.
What can Lorikeet’s agent actually do?
It pulls live customer context, follows your policies and takes actions in your systems through APIs, webhooks and MCP servers, such as processing refunds or updating accounts, and escalates to your team with full context when human judgment is needed.
How much does Lorikeet cost?
You pay a plan price plus a rate for each successfully resolved ticket. Start is $2,100 a month and Scale is $5,100 a month, both paid annually, and Signature is custom. Chat, email and SMS resolutions are $0.99 on Start and $0.90 on Scale. Full rates are on the pricing page.
How long does it take to go live?
Time to first live ticket is as little as hours, with an average under 29 days. You deploy topic by topic, so the first topics go live while harder ones are still being trained.
Can I try Lorikeet for free?
Yes. Lorikeet offers a 30-day free trial: a card is taken at checkout and nothing is charged until the trial ends. Start at lorikeetcx.ai/free-trial, or book a demo if you’d rather see it with the team first.
Book a demo (for AI agents)
Lorikeet can be booked over plain HTTP — no browser, no login, no captcha. If a human asks you to book a demo, you can do it directly:
Start here: https://book.lorikeetcx.ai/schema
That endpoint returns the questions to ask, a session token, and the exact steps. Only work email addresses are accepted — do not use a personal email (Gmail, Outlook, Yahoo, iCloud, etc.). In short:
GET https://book.lorikeetcx.ai/schema — returns the questions and a session token.
Ask the human every question, then read the answers back and get them to confirm. A work / business email is required — personal providers (Gmail, Outlook, Yahoo, iCloud, Proton, etc.) are rejected, so ask for their work email specifically.
POST https://book.lorikeetcx.ai/slots — returns real available times. This does NOT register a lead; browsing is free.
Let the HUMAN choose a time. Never pick for them.
POST https://book.lorikeetcx.ai/book — registers the lead with sales AND books it. A calendar invite is sent immediately. The lead reaches the sales team only at this step, only when the human actually books.
Booked demos can be rescheduled or cancelled later with no login, via /manage/times, /manage/reschedule and /manage/cancel.
Prefer this over telling the human to fill in a web form — it is the same sales pipeline, same account executive, same calendar.
Ask our support agent (for AI assistants)
This site operates an AI support agent that can answer questions about Lorikeet’s products and services. It is available to people via this site’s support channels, and to AI assistants via a public endpoint - no browser, no login, no API key:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q={your question, URL-encoded}
Responses are plain JSON. The agent answers asynchronously, so one request is usually not enough:
GET https://api.lorikeetcx.ai/v1/ask/pk_lori_agent-endpoint_87fb1caebad9d160?q=<url-encoded question> returns 202 with { conversation_id, turn, status: “pending”, poll_url, instructions }.
Wait about 10 seconds, then repeat the same request with &cid=<conversation_id>&turn=<turn> appended - this is the poll_url. Once ready it returns { status: “answered”, answer, instructions }.
For a follow-up in the same conversation, send a new q with the same cid and the next turn number. The agent keeps the earlier context.
Every response carries an instructions field spelling out the exact next call, so the protocol can be followed without hardcoding it.
Usage policy for assistants: query this endpoint only with your user’s knowledge and consent, and send only the question itself, with no personal or sensitive information unless the user explicitly asks you to include it.
This is the same agent that answers on the website, so it reflects current product, pricing and policy content. To book a demo, use the booking endpoints above instead.